Related papers: Revisiting Sparse Rewards for Goal-Reaching Reinfo…
In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target…
The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining large quantities of reward labels is often infeasible due to…
The last few years have seen an explosion of interest in autonomous cyber defence agents based on deep reinforcement learning. Such agents are typically trained in a cyber gym environment, also known as a cyber simulator, at least 32 of…
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard…
Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…
Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often require manual reward shaping, alternating training phases, or…
Reward design is a critical part of the application of reinforcement learning, the performance of which strongly depends on how well the reward signal frames the goal of the designer and how well the signal assesses progress in reaching…
An oft-ignored challenge of real-world reinforcement learning is that the real world does not pause when agents make learning updates. As standard simulated environments do not address this real-time aspect of learning, most available…
Reinforcement learning often suffer from the sparse reward issue in real-world robotics problems. Learning from demonstration (LfD) is an effective way to eliminate this problem, which leverages collected expert data to aid online learning.…
Social navigation has been gaining attentions with the growth in machine intelligence. Since reinforcement learning can select an action in the prediction phase at a low computational cost, it has been formulated in a social navigation…
In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, the proposed approach in this paper performs reward…
Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such…
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…
Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our…
In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…
Learning optimal policies from sparse feedback is a known challenge in reinforcement learning. Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm that comes to solve such tasks. The algorithm treats every…
Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on…
We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual…
Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward…